【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-31

发表于 2020-03-31 分类于 arxiv ， CV 195k 5:24

目录

1. DHP: Differentiable Meta Pruning via HyperNetworks [PDF] 摘要

2. Designing Network Design Spaces [PDF] 摘要

3. Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation [PDF] 摘要

4. Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging [PDF] 摘要

5. Vox2Vox: 3D-GAN for Brain Tumour Segmentation [PDF] 摘要

6. Supervised and Unsupervised Detections for Multiple Object Tracking in Traffic Scenes: A Comparative Study [PDF] 摘要

7. TResNet: High Performance GPU-Dedicated Architecture [PDF] 摘要

8. Laplacian Denoising Autoencoder [PDF] 摘要

9. Speech2Action: Cross-modal Supervision for Action Recognition [PDF] 摘要

10. Squeezed Deep 6DoF Object Detection Using Knowledge Distillation [PDF] 摘要

11. Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets [PDF] 摘要

12. Super Resolution for Root Imaging [PDF] 摘要

13. SiTGRU: Single-Tunnelled Gated Recurrent Unit for Abnormality Detection [PDF] 摘要

14. Improving out-of-distribution generalization via multi-task self-supervised pretraining [PDF] 摘要

15. LayoutMP3D: Layout Annotation of Matterport3D [PDF] 摘要

16. Improved Gradient based Adversarial Attacks for Quantized Networks [PDF] 摘要

17. A Comparison of Data Augmentation Techniques in Training Deep Neural Networks for Satellite Image Classification [PDF] 摘要

18. Faster than FAST: GPU-Accelerated Frontend for High-Speed VIO [PDF] 摘要

19. RPM-Net: Robust Point Matching using Learned Features [PDF] 摘要

20. DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning [PDF] 摘要

21. Computer Aided Detection for Pulmonary Embolism Challenge (CAD-PE) [PDF] 摘要

22. Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance [PDF] 摘要

23. Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks [PDF] 摘要

24. Context Based Emotion Recognition using EMOTIC Dataset [PDF] 摘要

25. Strip Pooling: Rethinking Spatial Pooling for Scene Parsing [PDF] 摘要

26. Active stereo vision three-dimensional reconstruction by RGB dot pattern projection and ray intersection [PDF] 摘要

27. Real-time Fruit Recognition and Grasp Estimation for Autonomous Apple harvesting [PDF] 摘要

28. Unsupervised Model Personalization while Preserving Privacy and Scalability: An Open Problem [PDF] 摘要

29. PANDA: Prototypical Unsupervised Domain Adaptation [PDF] 摘要

30. Multi-Objective Matrix Normalization for Fine-grained Visual Recognition [PDF] 摘要

31. Architecture Disentanglement for Deep Neural Networks [PDF] 摘要

32. Towards Palmprint Verification On Smartphones [PDF] 摘要

33. Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning [PDF] 摘要

34. TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge [PDF] 摘要

35. Memory Aggregation Networks for Efficient Interactive Video Object Segmentation [PDF] 摘要

36. Physical Model Guided Deep Image Deraining [PDF] 摘要

37. MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation [PDF] 摘要

38. Learning Memory-guided Normality for Anomaly Detection [PDF] 摘要

39. Learning to Learn Single Domain Generalization [PDF] 摘要

40. Cross-Domain Document Object Detection: Benchmark Suite and Method [PDF] 摘要

41. Density-Aware Graph for Deep Semi-Supervised Visual Recognition [PDF] 摘要

42. Adversarial Feature Hallucination Networks for Few-Shot Learning [PDF] 摘要

43. Incremental Learning In Online Scenario [PDF] 摘要

44. Gradually Vanishing Bridge for Adversarial Domain Adaptation [PDF] 摘要

45. Space-Time-Aware Multi-Resolution Video Enhancement [PDF] 摘要

46. Learning Interactions and Relationships between Movie Characters [PDF] 摘要

47. Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection [PDF] 摘要

48. Detection of 3D Bounding Boxes of Vehicles Using Perspective Transformation for Accurate Speed Measurement [PDF] 摘要

49. Defect segmentation: Mapping tunnel lining internal defects with ground penetrating radar data using a convolutional neural network [PDF] 摘要

50. High-Order Residual Network for Light Field Super-Resolution [PDF] 摘要

51. Disturbance-immune Weight Sharing for Neural Architecture Search [PDF] 摘要

52. Generative Partial Multi-View Clustering [PDF] 摘要

53. Structure-Preserving Super Resolution with Gradient Guidance [PDF] 摘要

54. Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation [PDF] 摘要

55. Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification [PDF] 摘要

56. Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation [PDF] 摘要

57. Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing [PDF] 摘要

58. Omni-sourced Webly-supervised Learning for Video Recognition [PDF] 摘要

59. Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds [PDF] 摘要

60. Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement [PDF] 摘要

61. Data-Driven Neuromorphic DRAM-based CNN and RNN Accelerators [PDF] 摘要

62. ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings [PDF] 摘要

63. Spatial Attention Pyramid Network for Unsupervised Domain Adaptation [PDF] 摘要

64. Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds [PDF] 摘要

65. GPS-Net: Graph Property Sensing Network for Scene Graph Generation [PDF] 摘要

66. Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose [PDF] 摘要

67. AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization [PDF] 摘要

68. Adaptive Object Detection with Dual Multi-Label Prediction [PDF] 摘要

69. Co-occurrence Background Model with Superpixels for Robust Background Initialization [PDF] 摘要

70. Superpixel Segmentation with Fully Convolutional Networks [PDF] 摘要

71. Refined Plane Segmentation for Cuboid-Shaped Objects by Leveraging Edge Detection [PDF] 摘要

72. One-Shot Domain Adaptation For Face Generation [PDF] 摘要

73. Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning [PDF] 摘要

74. Cross-domain Detection via Graph-induced Prototype Alignment [PDF] 摘要

75. CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Network [PDF] 摘要

76. Polarized Reflection Removal with Perfect Alignment in the Wild [PDF] 摘要

77. CNN-based Density Estimation and Crowd Counting: A Survey [PDF] 摘要

78. Real-MFF Dataset: A Large Realistic Multi-focus Image Dataset with Ground Truth [PDF] 摘要

79. Learning Invariant Representation for Unsupervised Image Restoration [PDF] 摘要

80. Trajectory Poisson multi-Bernoulli filters [PDF] 摘要

81. Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images [PDF] 摘要

82. A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising [PDF] 摘要

83. BiLingUNet: Image Segmentation by Modulating Top-Down and Bottom-Up Visual Processing with Referring Expressions [PDF] 摘要

84. Actor-Transformers for Group Activity Recognition [PDF] 摘要

85. Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognition [PDF] 摘要

86. NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing [PDF] 摘要

87. Semantically Mutil-modal Image Synthesis [PDF] 摘要

88. Using the Split Bregman Algorithm to Solve the Self-Repelling Snake Model [PDF] 摘要

89. Inferring Semantic Information with 3D Neural Scene Representations [PDF] 摘要

90. Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement [PDF] 摘要

91. Designing Color Filters that Make Cameras MoreColorimetric [PDF] 摘要

92. Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images [PDF] 摘要

93. Self-Supervised Learning for Domain Adaptation on Point-Clouds [PDF] 摘要

94. Combining Visible and Infrared Spectrum Imagery using Machine Learning for Small Unmanned Aerial System Detection [PDF] 摘要

95. Detection and Description of Change in Visual Streams [PDF] 摘要

96. MCFlow: Monte Carlo Flow Models for Data Imputation [PDF] 摘要

97. On the Evaluation of Prohibited Item Classification and Detection in Volumetric 3D Computed Tomography Baggage Security Screening Imagery [PDF] 摘要

98. SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans [PDF] 摘要

99. Acceleration of Convolutional Neural Network Using FFT-Based Split Convolutions [PDF] 摘要

100. Source Printer Identification from Document Images Acquired using Smartphone [PDF] 摘要

101. Weakly-supervised land classification for coastal zone based on deep convolutional neural networks by incorporating dual-polarimetric characteristics into training dataset [PDF] 摘要

102. How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference [PDF] 摘要

103. BVI-DVC: A Training Database for Deep Video Compression [PDF] 摘要

104. OCmst: One-class Novelty Detection using Convolutional Neural Network and Minimum Spanning Trees [PDF] 摘要

105. Diagnosis of Breast Cancer using Hybrid Transfer Learning [PDF] 摘要

106. Interval Neural Networks as Instability Detectors for Image Reconstructions [PDF] 摘要

107. PointGMM: a Neural GMM Network for Point Clouds [PDF] 摘要

108. Optimizing Geometry Compression using Quantum Annealing [PDF] 摘要

109. InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining [PDF] 摘要

110. Can AI help in screening Viral and COVID-19 pneumonia? [PDF] 摘要

111. Unsupervised Deep Learning for MR Angiography with Flexible Temporal Resolution [PDF] 摘要

112. Mutual Learning Network for Multi-Source Domain Adaptation [PDF] 摘要

113. NPENAS: Neural Predictor Guided Evolution for Neural Architecture Search [PDF] 摘要

114. A Benchmark for Point Clouds Registration Algorithms [PDF] 摘要

115. Gradient-based Data Augmentation for Semi-Supervised Learning [PDF] 摘要

116. Adversarial Imitation Attack [PDF] 摘要

117. Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework [PDF] 摘要

118. DaST: Data-free Substitute Training for Adversarial Attacks [PDF] 摘要

119. Learning to Smooth and Fold Real Fabric Using Dense Object Descriptors Trained on Synthetic Color Images [PDF] 摘要

120. Image compression optimized for 3D reconstruction by utilizing deep neural networks [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-31

发表于 2020-03-31 分类于 arxiv ， CL 45k 1:15

目录

1. European Language Grid: An Overview [PDF] 摘要

2. QRMine: A python package for triangulation in Grounded Theory [PDF] 摘要

3. Empirical Analysis of Zipf's Law, Power Law, and Lognormal Distributions in Medical Discharge Reports [PDF] 摘要

4. A Corpus of Controlled Opinionated and Knowledgeable Movie Discussions for Training Neural Conversation Models [PDF] 摘要

5. Investigating Language Impact in Bilingual Approaches for Computational Language Documentation [PDF] 摘要

6. How human judgment impairs automated deception detection performance [PDF] 摘要

7. Making Metadata Fit for Next Generation Language Technology Platforms: The Metadata Schema of the European Language Grid [PDF] 摘要

8. Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation [PDF] 摘要

9. InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining [PDF] 摘要

10. Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement [PDF] 摘要

11. Named Entities in Medical Case Reports: Corpus and Experiments [PDF] 摘要

12. Abstractive Summarization with Combination of Pre-trained Sequence-to-Sequence and Saliency Models [PDF] 摘要

13. Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling [PDF] 摘要

14. A Dataset of German Legal Documents for Named Entity Recognition [PDF] 摘要

15. Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining [PDF] 摘要

16. User Generated Data: Achilles' heel of BERT [PDF] 摘要

17. Orchestrating NLP Services for the Legal Domain [PDF] 摘要

18. Unsupervised feature learning for speech using correspondence and Siamese networks [PDF] 摘要

19. HIN: Hierarchical Inference Network for Document-Level Relation Extraction [PDF] 摘要

20. Variational Transformers for Diverse Response Generation [PDF] 摘要

21. A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency [PDF] 摘要

22. Serialized Output Training for End-to-End Overlapped Speech Recognition [PDF] 摘要

23. Towards Supervised and Unsupervised Neural Machine Translation Baselines for Nigerian Pidgin [PDF] 摘要

24. TREC CAsT 2019: The Conversational Assistance Track Overview [PDF] 摘要

25. Using News Articles and Financial Data to predict the likelihood of bankruptcy [PDF] 摘要

26. AliCoCo: Alibaba E-commerce Cognitive Concept Net [PDF] 摘要

27. A Novel Method of Extracting Topological Features from Word Embeddings [PDF] 摘要

28. BiLingUNet: Image Segmentation by Modulating Top-Down and Bottom-Up Visual Processing with Referring Expressions [PDF] 摘要

29. Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework [PDF] 摘要

30. Countering Language Drift with Seeded Iterated Learning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-30

发表于 2020-03-30 分类于 arxiv ， CV 66k 1:50

目录

1. Probabilistic Regression for Visual Tracking [PDF] 摘要

2. DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search [PDF] 摘要

3. Assessing Image Quality Issues for Real-World Problem [PDF] 摘要

4. Hybrid Models for Open Set Recognition [PDF] 摘要

5. End-to-end Autonomous Driving Perception with Sequential Latent Representation Learning [PDF] 摘要

6. TextCaps: a Dataset for Image Captioning with Reading Comprehension [PDF] 摘要

7. Weakly-Supervised Action Localization by Generative Attention Modeling [PDF] 摘要

8. Learning Implicit Surface Light Fields [PDF] 摘要

9. Modeling 3D Shapes by Reinforcement Learning [PDF] 摘要

10. PyMatting: A Python Library for Alpha Matting [PDF] 摘要

11. Enhanced Self-Perception in Mixed Reality: Egocentric Arm Segmentation and Database with Automatic Labelling [PDF] 摘要

12. Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction [PDF] 摘要

13. Tackling Two Challenges of 6D Object Pose Estimation: Lack of Real Annotated RGB Images and Scalability to Number of Objects [PDF] 摘要

14. An Investigation into the Stochasticity of Batch Whitening [PDF] 摘要

15. Lightweight Photometric Stereo for Facial Details Recovery [PDF] 摘要

16. CurlingNet: Compositional Learning between Images and Text for Fashion IQ Data [PDF] 摘要

17. Generalizable Semantic Segmentation via Model-agnostic Learning and Target-specific Normalization [PDF] 摘要

18. Towards Accurate Scene Text Recognition with Semantic Reasoning Networks [PDF] 摘要

19. Controllable Person Image Synthesis with Attribute-Decomposed GAN [PDF] 摘要

20. Weakly Supervised Dataset Collection for Robust Person Detection [PDF] 摘要

21. One-Shot GAN Generated Fake Face Detection [PDF] 摘要

22. Dynamic Region-Aware Convolution [PDF] 摘要

23. Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations [PDF] 摘要

24. Learning to Optimize Non-Rigid Tracking [PDF] 摘要

25. Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification [PDF] 摘要

26. HERS: Homomorphically Encrypted Representation Search [PDF] 摘要

27. Action Localization through Continual Predictive Learning [PDF] 摘要

28. ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds [PDF] 摘要

29. An improved 3D region detection network: automated detection of the 12th thoracic vertebra in image guided radiation therapy [PDF] 摘要

30. Cycle Text-To-Image GAN with BERT [PDF] 摘要

31. SaccadeNet: A Fast and Accurate Object Detector [PDF] 摘要

32. Real-time information retrieval from Identity cards [PDF] 摘要

33. Local Facial Makeup Transfer via Disentangled Representation [PDF] 摘要

34. Augmenting Colonoscopy using Extended and Directional CycleGAN for Lossy Image Translation [PDF] 摘要

35. A Computer-Aided Diagnosis System Using Artificial Intelligence for Proximal Femoral Fractures Enables Residents to Achieve a Diagnostic Rate Equivalent to Orthopedic Surgeons -- multi-institutional joint development research [PDF] 摘要

36. End-to-End Entity Classification on Multimodal Knowledge Graphs [PDF] 摘要

37. COVID-19 Screening on Chest X-ray Images Using Deep Learning based Anomaly Detection [PDF] 摘要

38. A Comprehensive Review for Breast Histopathology Image Analysis Using Classical and Deep Neural Networks [PDF] 摘要

39. MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation [PDF] 摘要

40. Going in circles is the way forward: the role of recurrence in visual inference [PDF] 摘要

41. Pedestrian Detection with Wearable Cameras for the Blind: A Two-way Perspective [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-30

发表于 2020-03-30 分类于 arxiv ， CL 16k 26 分钟

目录

1. Semantic Enrichment of Nigerian Pidgin English for Contextual Sentiment Classification [PDF] 摘要

2. Information-Theoretic Probing with Minimum Description Length [PDF] 摘要

3. Comprehensive Named Entity Recognition on CORD-19 with Distant or Weak Supervision [PDF] 摘要

4. Integrating Crowdsourcing and Active Learning for Classification of Work-Life Events from Tweets [PDF] 摘要

5. FFR V1.0: Fon-French Neural Machine Translation [PDF] 摘要

6. TextCaps: a Dataset for Image Captioning with Reading Comprehension [PDF] 摘要

7. End-to-End Entity Classification on Multimodal Knowledge Graphs [PDF] 摘要

8. Can you hear me $\textit{now}$? Sensitive comparisons of human and machine perception [PDF] 摘要

9. Knowledge Graph Alignment using String Edit Distance [PDF] 摘要

10. Machine learning as a model for cultural learning: Teaching an algorithm what it means to be fat [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-27

发表于 2020-03-27 分类于 arxiv ， CV 72k 2:01

目录

1. Memory Enhanced Global-Local Aggregation for Video Object Detection [PDF] 摘要

2. Negative Margin Matters: Understanding Margin in Few-shot Classification [PDF] 摘要

3. Correspondence Networks with Adaptive Neighbourhood Consensus [PDF] 摘要

4. Grounded Situation Recognition [PDF] 摘要

5. Are Labels Necessary for Neural Architecture Search? [PDF] 摘要

6. Learning Inverse Rendering of Faces from Real-world Videos [PDF] 摘要

7. Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects [PDF] 摘要

8. Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol [PDF] 摘要

9. Pseudo-Labeling for Small Lesion Detection on Diabetic Retinopathy Images [PDF] 摘要

10. RAFT: Recurrent All-Pairs Field Transforms for Optical Flow [PDF] 摘要

11. Convolutional Neural Networks for Image-based Corn Kernel Detection and Counting [PDF] 摘要

12. Milking CowMask for Semi-Supervised Image Classification [PDF] 摘要

13. Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images [PDF] 摘要

14. Towards Backward-Compatible Representation Learning [PDF] 摘要

15. Zero-Assignment Constraint for Graph Matching with Outliers [PDF] 摘要

16. Matrix Smoothing: A Regularization for DNN with Transition Matrix under Noisy Labels [PDF] 摘要

17. DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation [PDF] 摘要

18. Instance Credibility Inference for Few-Shot Learning [PDF] 摘要

19. P $\approx$ NP, at least in Visual Question Answering [PDF] 摘要

20. Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection [PDF] 摘要

21. Do Deep Minds Think Alike? Selective Adversarial Attacks for Fine-Grained Manipulation of Multiple Deep Neural Networks [PDF] 摘要

22. Neural encoding and interpretation for high-level visual cortices based on fMRI using image caption features [PDF] 摘要

23. Compact Deep Aggregation for Set Retrieval [PDF] 摘要

24. Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space [PDF] 摘要

25. The 1st Challenge on Remote Physiological Signal Sensing (RePSS) [PDF] 摘要

26. Real-time 3D Deep Multi-Camera Tracking [PDF] 摘要

27. Egoshots, an ego-vision life-logging dataset and semantic fidelity metric to evaluate diversity in image captioning models [PDF] 摘要

28. Fastidious Attention Network for Navel Orange Segmentation [PDF] 摘要

29. Mask Encoding for Single Shot Instance Segmentation [PDF] 摘要

30. Classification of the Chinese Handwritten Numbers with Supervised Projective Dictionary Pair Learning [PDF] 摘要

31. BachGAN: High-Resolution Image Synthesis from Salient Object Layout [PDF] 摘要

32. DeepStrip: High Resolution Boundary Refinement [PDF] 摘要

33. Deep Grouping Model for Unified Perceptual Parsing [PDF] 摘要

34. VIOLIN: A Large-Scale Dataset for Video-and-Language Inference [PDF] 摘要

35. Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis [PDF] 摘要

36. GISNet: Graph-Based Information Sharing Network For Vehicle Trajectory Prediction [PDF] 摘要

37. Coronary Artery Segmentation in Angiographic Videos Using A 3D-2D CE-Net [PDF] 摘要

38. Weakly-supervised 3D coronary artery reconstruction from two-view angiographic images [PDF] 摘要

39. Robust Classification of High-Dimensional Spectroscopy Data Using Deep Learning and Data Synthesis [PDF] 摘要

40. DeepCrashTest: Turning Dashcam Videos into Virtual Crash Tests for Automated Driving Systems [PDF] 摘要

41. iTAML: An Incremental Task-Agnostic Meta-learning Approach [PDF] 摘要

42. Stochastic reconstruction of periodic, three-dimensional multi-phase electrode microstructures using generative adversarial networks [PDF] 摘要

43. Covid-19: Automatic detection from X-Ray images utilizing Transfer Learning with Convolutional Neural Networks [PDF] 摘要

44. COVID-19 Image Data Collection [PDF] 摘要

45. Learning to Correct Overexposed and Underexposed Photos [PDF] 摘要

46. Interval Neural Networks: Uncertainty Scores [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-27

发表于 2020-03-27 分类于 arxiv ， CL 19k 32 分钟

目录

1. TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation [PDF] 摘要

2. Rat big, cat eaten! Ideas for a useful deep-agent protolanguage [PDF] 摘要

3. Common-Knowledge Concept Recognition for SEVA [PDF] 摘要

4. Word2Vec: Optimal Hyper-Parameters and Their Impact on NLP Downstream Tasks [PDF] 摘要

5. Multi-Label Text Classification using Attention-based Graph Neural Network [PDF] 摘要

6. Sentiment Analysis in Drug Reviews using Supervised Machine Learning Algorithms [PDF] 摘要

7. Author2Vec: A Framework for Generating User Embedding [PDF] 摘要

8. Predicting Unplanned Readmissions with Highly Unstructured Data [PDF] 摘要

9. Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Data [PDF] 摘要

10. Finnish Language Modeling with Deep Transformer Models [PDF] 摘要

11. Predicting Legal Proceedings Status: an Approach Based on Sequential Text Data [PDF] 摘要

12. Forensic Authorship Analysis of Microblogging Texts Using N-Grams and Stylometric Features [PDF] 摘要

13. VIOLIN: A Large-Scale Dataset for Video-and-Language Inference [PDF] 摘要

14. Heavy-tailed Representations, Text Polarity Classification & Data Augmentation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-26

发表于 2020-03-26 分类于 arxiv ， CV 71k 1:59

目录

1. Learning What to Learn for Video Object Segmentation [PDF] 摘要

2. Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? [PDF] 摘要

3. HP2IFS: Head Pose estimation exploiting Partitioned Iterated Function Systems [PDF] 摘要

4. Training Binary Neural Networks with Real-to-Binary Convolutions [PDF] 摘要

5. Improved Techniques for Training Single-Image GANs [PDF] 摘要

6. PiP: Planning-informed Trajectory Prediction for Autonomous Driving [PDF] 摘要

7. Fisheye Distortion Rectification from Deep Straight Lines [PDF] 摘要

8. Circumventing Outliers of AutoAugment with Knowledge Distillation [PDF] 摘要

9. Data Uncertainty Learning in Face Recognition [PDF] 摘要

10. SPFCN: Select and Prune the Fully Convolutional Networks for Real-time Parking Slot Detection [PDF] 摘要

11. DCDLearn: Multi-order Deep Cross-distance Learning for Vehicle Re-Identification [PDF] 摘要

12. Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation [PDF] 摘要

13. A Unified Object Motion and Affinity Model for Online Multi-Object Tracking [PDF] 摘要

14. SCATTER: Selective Context Attentional Scene Text Recognizer [PDF] 摘要

15. Multiscale Sparsifying Transform Learning for Image Denoising [PDF] 摘要

16. VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning [PDF] 摘要

17. What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective [PDF] 摘要

18. GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet [PDF] 摘要

19. ASFD: Automatic and Scalable Face Detector [PDF] 摘要

20. A New Multiple Max-pooling Integration Module and Cross Multiscale Deconvolution Network Based on Image Semantic Segmentation [PDF] 摘要

21. Two-stage Discriminative Re-ranking for Large-scale Landmark Retrieval [PDF] 摘要

22. Prior-enlightened and Motion-robust Video Deblurring [PDF] 摘要

23. Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset [PDF] 摘要

24. Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach [PDF] 摘要

25. A Systematic Evaluation: Fine-Grained CNN vs. Traditional CNN Classifiers [PDF] 摘要

26. Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Study [PDF] 摘要

27. BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models [PDF] 摘要

28. Joint Deep Cross-Domain Transfer Learning for Emotion Recognition [PDF] 摘要

29. PADS: Policy-Adapted Sampling for Visual Similarity Learning [PDF] 摘要

30. G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features [PDF] 摘要

31. Bootstrapping Weakly Supervised Segmentation-free Word Spotting through HMM-based Alignment [PDF] 摘要

32. A Survey of Methods for Low-Power Deep Learning and Computer Vision [PDF] 摘要

33. Deformable Style Transfer [PDF] 摘要

34. Visual-Inertial Telepresence for Aerial Manipulation [PDF] 摘要

35. Not all domains are equally complex: Adaptive Multi-Domain Learning [PDF] 摘要

36. Commentaries on "Learning Sensorimotor Control with Neuromorphic Sensors: Toward Hyperdimensional Active Perception" [Science Robotics Vol. 4 Issue 30 (2019) 1-10 [PDF] 摘要

37. Content Adaptive and Error Propagation Aware Deep Video Compression [PDF] 摘要

38. Safety-Aware Hardening of 3D Object Detection Neural Network Systems [PDF] 摘要

39. Aerial Imagery based LIDAR Localization for Autonomous Vehicles [PDF] 摘要

40. Patch-based Non-Local Bayesian Networks for Blind Confocal Microscopy Denoising [PDF] 摘要

41. PoisHygiene: Detecting and Mitigating Poisoning Attacks in Neural Networks [PDF] 摘要

42. Removing Dynamic Objects for Static Scene Reconstruction using Light Fields [PDF] 摘要

43. ML-SIM: A deep neural network for reconstruction of structured illumination microscopy images [PDF] 摘要

44. COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images [PDF] 摘要

45. CoCoPIE: Making Mobile AI Sweet As PIE --Compression-Compilation Co-Design Goes a Long Way [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-26

发表于 2020-03-26 分类于 arxiv ， CL 30k 50 分钟

目录

1. The Medical Scribe: Corpus Development and Model Performance Analyses [PDF] 摘要

2. Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation [PDF] 摘要

3. Masakhane -- Machine Translation For Africa [PDF] 摘要

4. Generating Major Types of Chinese Classical Poetry in a Uniformed Framework [PDF] 摘要

5. Tigrinya Neural Machine Translation with Transfer Learning for Humanitarian Response [PDF] 摘要

6. Matching Text with Deep Mutual Information Estimation [PDF] 摘要

7. Joint Multiclass Debiasing of Word Embeddings [PDF] 摘要

8. Vector logic and counterfactuals [PDF] 摘要

9. Hybrid Attention-Based Transformer Block Model for Distant Supervision Relation Extraction [PDF] 摘要

10. From Algebraic Word Problem to Program: A Formalized Approach [PDF] 摘要

11. Keyword-Attentive Deep Semantic Matching [PDF] 摘要

12. Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings [PDF] 摘要

13. BaitWatcher: A lightweight web interface for the detection of incongruent news headlines [PDF] 摘要

14. Adversarial Multi-Binary Neural Network for Multi-class Classification [PDF] 摘要

15. Learning Syntactic and Dynamic Selective Encoding for Document Summarization [PDF] 摘要

16. Can Embeddings Adequately Represent Medical Terminology? New Large-Scale Medical Term Similarity Datasets Have the Answer! [PDF] 摘要

17. XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization [PDF] 摘要

18. Utilizing Deep Learning to Identify Drug Use on Twitter Data [PDF] 摘要

19. COVID-19 and Computer Audition: An Overview on What Speech & Sound Analysis Could Contribute in the SARS-CoV-2 Corona Crisis [PDF] 摘要

20. EQL -- an extremely easy to learn knowledge graph query language, achieving highspeed and precise search [PDF] 摘要

阅读全文 »